Database Open Access

I-CARE: International Cardiac Arrest REsearch consortium Database

Edilberto Amorim Wei-Long Zheng Jong Woo Lee Susan Herman Mohammad Ghassemi Adithya Sivaraju Nicolas Gaspard Jeannette Hofmeijer Michel J A M van Putten Matthew Reyna Gari Clifford Brandon Westover

Published: June 16, 2023. Version: 2.0 <View latest version>


When using this resource, please cite: (show more options)
Amorim, E., Zheng, W., Lee, J. W., Herman, S., Ghassemi, M., Sivaraju, A., Gaspard, N., Hofmeijer, J., van Putten, M. J. A. M., Reyna, M., Clifford, G., & Westover, B. (2023). I-CARE: International Cardiac Arrest REsearch consortium Database (version 2.0). PhysioNet. https://doi.org/10.13026/avek-0p97.

Please include the standard citation for PhysioNet: (show more options)
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

Abstract

The International Cardiac Arrest REsearch consortium (I-CARE) Database includes baseline clinical information and continuous electroencephalogram (EEG) and electrocardiogram (ECG) recordings from comatose patients following cardiac arrest. The patients were admitted to an intensive care unit (ICU) in one of seven academic hospitals in the U.S. and Europe and monitored for several hours to several days. The long-term neurological function of the patients was determined using the Cerebral Performance Category scale.


Background

More than 6 million cardiac arrests happen every year worldwide, with survival rates ranging from 1% to 10% depending on geographic location [1]. Severe brain injury is the main determinant of poor outcome for patients surviving cardiac arrest resuscitation [1,2]. Most patients surviving to ICU admission will be comatose, and 50% to 80% will have life-sustaining therapies withdrawn due to a perceived poor neurological prognosis [3]. 

Brain monitoring with EEG aims to reduce the subjectivity in neurologic prognostication following cardiac arrest [4-9]. Clinical neurophysiologists have identified numerous patterns of brain activity that help to predict prognosis following cardiac arrest, including the presences of reduced voltage, burst suppression (alternating periods of high and low voltage), seizures, and a variety of seizure-like patterns [8]. The evolution of EEG patterns over time may provide additional predictive information [6,7]. However, qualitative interpretation of continuous EEG is laborious, expensive, and requires review from neurologists with advanced training in neurophysiology who are unavailable in most medical centers.

Automated analysis of continuous EEG and other data has the potential to improve prognostic accuracy and to increase access to brain monitoring where experts are not readily available [6,7]. However, the datasets used in most studies typically only have small numbers of patients (<100) from single hospitals, which are unsuitable for deployment of several types of machine learning methods for EEG data analysis. To overcome this limitation the International Cardiac Arrest REsearch consortium (I-CARE) assembled a large collection of clinical, EEG, and ECG data with neurologic outcomes from comatose patients following cardiac arrest. The I-CARE dataset includes seven hospitals from the United States and Europe. 


Methods

The database originates from seven academic hospitals in the U.S. and Europe led by investigators part of the International Cardiac Arrest REsearch consortium (I-CARE).

  1. Rijnstate Hospital, Arnhem, The Netherlands (Jeannette Hofmeijer).
  2. Medisch Spectrum Twente, Enschede, The Netherlands (Barry J. Ruijter, Marleen C. Tjepkema-Cloostermans, Michel J. A. M. van Putten).
  3. Erasme Hospital, Brussels, Belgium (Nicolas Gaspard).
  4. Massachusetts General Hospital, Boston, Massachusetts, USA (Edilberto Amorim, Wei-Long Zheng, Mohammad Ghassemi, and M. Brandon Westover).
  5. Brigham and Women’s Hospital, Boston, Massachusetts, USA (Jong Woo Lee).
  6. Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA (Susan T. Herman).
  7. Yale New Haven Hospital, New Haven, Connecticut, USA (Adithya Sivaraju).

This database consists of clinical, EEG, and ECG data from adult patients with out-of-hospital or in-hospital cardiac arrest who had return of heart function (i.e., return of spontaneous circulation [ROSC]) but remained comatose - defined as the inability to follow verbal commands and a Glasgow Coma Score inferior or equal to 8.

The initial database release contains data for over 32,712 hours of data in 80,809 recording segments from 607 patients - this is the public training set for the George B. Moody PhysioNet Challenge 2023. This database release does not contain data from the remaining 413 patients that we are retaining as the hidden validation and test sets for the Challenge.

All patients were admitted to an ICU and had their brain activity monitored with continuous EEG. Monitoring was typically started within hours of cardiac arrest and continued for several hours to several days depending on the patient's condition, so the recording start time and duration varies from patient to patient. This database includes EEG data and, when possible, ECG data for each patient. This project contains the part of the database that we have shared as a public training set for the PhysioNet Challenge 2023; the remainder of the database has been retained as private validation and test sets for the Challenge. Data from one hospital system were omitted from the training and validation sets to assess generalizability to unseen data.

Clinical Data

Patient information recorded at the time of admission (age, sex, and a hospital identifier), location of arrest (out or in-hospital), type of cardiac rhythm recorded at the time of resuscitation (shockable rhythms include ventricular fibrillation or ventricular tachycardia and non-shockable rhythms include asystole and pulseless electrical activity), and the time between cardiac arrest and ROSC. Patient temperature after cardiac arrest is controlled using a closed-loop feedback device (TTM) in most patients unless there are contraindications such as severe and difficult to control hypotension or delay in hospital admission. For patients undergoing TTM, the temperature level can be controlled at either 36 or 33 degrees Celsius.

Neurological Prognostication and Outcome Assessment

All participating hospitals have protocols for multimodal neurological prognostication that follow international guideline recommendations. Formal neurological prognostication is deferred until the normothermia phase and confounding from sedatives can be minimized.

Patient Outcomes

Clinical outcome was determined prospectively in two centers by phone interview (at 6 months from ROSC), and at the remaining five hospitals retrospectively through chart review (at 3-6 months from ROSC). Neurological function was determined using the best Cerebral Performance Category (CPC) scale [10]. CPC is an ordinal scale ranging from 1 to 5, ranging from good neurological function to death.

De-identification

Clinical and EEG data were de-identified. Patients with age above 89 years old are listed with age "90". EEG timestamps are organized based on the time elapsed since ROSC. The hospital identifiers do not identify the hospital name.


Data Description

EEG Data

All EEG signal data are provided in WFDB format, with the signal data are stored in MATLAB MAT files (MAT v4 format). For example, the binary signal file 0284_001_004_EEG.mat contains the first segment of the EEG signal data, starting at 4 hours, 7 minutes, and 23 seconds after cardiac arrest and ending at 4 hours, 59 minutes, and 59 seconds after cardiac arrest, for patient 0284 of the I-CARE patient cohort. The plain text header file 0284_001_004_EEG.hea describes the contents of this signal file as well as the start time, stop time, and utility frequency (i.e., powerline frequency or mains frequency) for the data.

When possible, the channel names have been standardized between and within different hospitals. Different channels are available for different hospitals and different patients, including those from the same hospital. Even when a channel has been provided, it may be disconnected or noisy. The channels are organized into an EEG group, an ECG group, a reference (REF) group, and an other (OTHER) group:

  • EEG: Fp1, Fp2, F7, F8, F3, F4, T3, T4, C3, C4, T5, T6, P3, P4, O1, O2, Fz, Cz, Pz, Fpz, Oz, F9
  • ECG: ECG, ECG1, ECG2, ECGL, ECGR
  • REF: RAT1, RAT2, REF, C2, A1, A2, BIP1, BIP2, BIP3, BIP4, Cb2, M1, M2, In1-Ref2, In1-Ref3
  • OTHER: SpO2, EMG1, EMG2, EMG3, LAT1, LAT2, LOC, ROC, LEG1, LEG2

The recordings were segmented so that each segment ends at the hour, or the end of the recording, whichever occurs first. Noisy recordings with artifacts were intentionally preserved [11].

Clinical Data and Patient Outcome

The following clinical data is contained in each .txt file: 

Age (in years): Number

Sex: Male, Female

Hospital: A, B, C, D, E, F

ROSC (return of spontaneous circulation, in minutes): Time from cardiac arrest to return of spontaneous circulation

OHCA (out-of-hospital cardiac arrest): True = out of hospital cardiac arrest, False = in-hospital cardiac arrest

Shockable Rhythm: True = shockable rhythm, False = non-shockable rhythm

TTM (targeted temperature management; in Celsius): 33, 36, or NaN for no TTM

Outcome: Good (CPC score of 1-2), Poor (CPC score of 3-5)

CPC: Cerebral Performance Category (CPC) score (ordinal scale 1-5)

  • CPC = 1: good neurological function and independent for activities of daily living 
  • CPC = 2: moderate neurological disability but independent for activities of daily living
  • CPC = 3: severe neurological disability
  • CPC = 4: unresponsive wakefulness syndrome [previously known as vegetative state] 
  • CPC = 5: dead. 

We have grouped CPC scores in two categories: 

  • “Good outcome”: CPC = 1 or 2
  • “Poor outcome”: CPC = 3, 4, or 5

Usage Notes

These data are in a WFDB-compatible format, and WFDB packages can be used to read them. 

We have implemented example prediction algorithms in MATLAB and Python that read the data:

  • MATLAB example at [12].
  • Python example at [13].

Release Notes

By downloading the data, you agree not to repost the data or to publish or otherwise share any work that uses the data, in full or in part, before the end of the PhysioNet Challenge 2023 except to the Computing in Cardiology conference.


Ethics

Data collection and analysis was performed under independent Institutional Review Board approvals at participating hospitals, and a data sharing agreement was made among participating hospitals. This was a retrospective analysis of data obtained as part of the usual care and the requirement for informed consent was waived.


Acknowledgements

This study was supported by the American Heart Association (20CDA35310297), CURE Epilepsy Foundation (Taking Flight Award), Neurocritical Care Society (NCS research training fellowship), Weil-Society of Critical Care Medicine Research Grant, the NIH (1K23NS090900, 1R01NS102190, 1R01NS102574, 1R01NS107291, 1K23NS119794, R01EB030362), Epilepsiefonds (NEF 14-18), and Dutch Heart Foundation (2018T070).


Conflicts of Interest

M.V.P. is founder of Clinical Science Systems. Clinical Science Systems did not contribute funding nor played any role in the study. M.B.W. is a co-founder of Beacon Biosignals. Beacon Biosignals neither contributed funding nor played any role in the study.


References

  1. Yan, S., Gan, Y., Jiang, N. et al. The global survival rate among adult out-of-hospital cardiac arrest patients who received cardiopulmonary resuscitation: a systematic review and meta-analysis. Crit Care 24, 61 (2020). https://doi.org/10.1186/s13054-020-2773-2.
  2. Dankiewicz J, Cronberg T, Lilja G, et al. Hypothermia versus Normothermia after Out-of-Hospital Cardiac Arrest. N Engl J Med. 2021;384:2283–2294.
  3. Elmer J, Torres C, Aufderheide TP, Austin MA, Callaway CW, Golan E, Herren H, Jasti J, Kudenchuk PJ, Scales DC, Stub D, Richardson DK, Zive DM; Resuscitation Outcomes Consortium. Association of early withdrawal of life-sustaining therapy for perceived neurological prognosis with mortality after cardiac arrest. Resuscitation. 2016 May;102:127-35. doi: 10.1016/j.resuscitation.2016.01.016. Epub 2016 Feb 3. PMID: 26836944; PMCID: PMC4834233.
  4. Amorim E, Rittenberger JC, Zheng JJ, et al. Continuous EEG monitoring enhances multimodal outcome prediction in hypoxic-ischemic brain injury. Resuscitation. 2016;109:121–126.
  5. Hofmeijer J, Beernink TMJ, Bosch FH, Beishuizen A, Tjepkema-Cloostermans MC, van Putten MJAM. Early EEG contributes to multimodal outcome prediction of postanoxic coma. Neurology. 2015;85:137–143.
  6. Zheng W-L, Amorim E, Jing J, et al. Predicting neurological outcome in comatose patients after cardiac arrest with multiscale deep neural networks. Resuscitation. 2021;169:86–94.
  7. Zheng W-L, Amorim E, Jing J, et al. Predicting Neurological Outcome from Electroencephalogram Dynamics in Comatose Patients after Cardiac Arrest with Deep Learning. IEEE Trans Biomed Eng. Epub 2021.:1–1.
  8. Khazanova D, Douglas VC, Amorim E. A matter of timing: EEG monitoring for neurological prognostication after cardiac arrest in the era of targeted temperature management. Minerva Anestesiol. 2021;87:704–713.
  9. Ruijter BJ, van Putten MJAM, van den Bergh WM, Tromp SC, Hofmeijer J. Propofol does not affect the reliability of early EEG for outcome prediction of comatose patients after cardiac arrest. Clin Neurophysiol Off J Int Fed Clin Neurophysiol. 2019;130:1263–1270.
  10. Taccone FS, Horn J, Storm C, et al. Death after awakening from post-anoxic coma: the “Best CPC” project. Crit Care Lond Engl. 2019;23:107.
  11. International Cardiac Arrest EEG Consortium (ICARE) Dataset with Deep Learning. https://github.com/bdsp-core/icare-dl.
  12. PhysioNet 2023 Challenge MATLAB Example. https://github.com/physionetchallenges/matlab-example-2023
  13. PhysioNet 2023 Challenge Python Example. https://github.com/physionetchallenges/python-example-2023

Share
Access

Access Policy:
Anyone can access the files, as long as they conform to the terms of the specified license.

License (for files):
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License

Discovery
Corresponding Author
You must be logged in to view the contact information.
Versions
  • 1.0 - Feb. 21, 2023
  • 2.0 - June 16, 2023
  • 2.1 - Dec. 14, 2023

Files

Total uncompressed size: 1.5 TB.

Access the files

Visualize waveforms

Folder Navigation: <base>/training
Name Size Modified
Parent Directory
0284
0286
0296
0299
0303
0306
0311
0312
0313
0316
0319
0320
0326
0328
0332
0334
0335
0337
0340
0341
0342
0344
0346
0347
0348
0349
0350
0351
0352
0353
0354
0355
0356
0357
0358
0359
0360
0361
0362
0363
0364
0365
0366
0367
0368
0369
0370
0371
0372
0373
0375
0376
0377
0378
0379
0380
0382
0383
0384
0385
0387
0389
0390
0391
0392
0394
0395
0396
0397
0398
0399
0400
0402
0403
0404
0405
0406
0407
0409
0410
0411
0412
0413
0414
0415
0416
0417
0418
0419
0420
0421
0422
0423
0424
0426
0427
0428
0429
0430
0431
0432
0433
0434
0435
0436
0437
0438
0439
0440
0441
0442
0443
0444
0445
0446
0447
0448
0450
0451
0452
0453
0455
0456
0457
0458
0459
0460
0461
0462
0463
0464
0465
0466
0467
0468
0469
0470
0471
0472
0473
0474
0475
0476
0477
0479
0481
0482
0483
0484
0485
0486
0487
0490
0492
0493
0495
0496
0497
0498
0500
0501
0502
0504
0505
0506
0507
0508
0510
0512
0513
0514
0515
0517
0518
0519
0520
0521
0522
0523
0525
0526
0527
0529
0530
0531
0532
0533
0535
0536
0538
0539
0540
0541
0542
0543
0544
0545
0546
0547
0548
0549
0550
0552
0553
0554
0555
0556
0558
0559
0560
0561
0562
0563
0564
0565
0566
0567
0568
0569
0570
0571
0573
0574
0575
0576
0577
0579
0580
0582
0584
0585
0586
0587
0588
0589
0590
0591
0592
0593
0595
0597
0598
0600
0601
0602
0604
0605
0606
0607
0609
0610
0611
0612
0613
0614
0615
0616
0617
0618
0619
0621
0623
0624
0625
0626
0627
0628
0629
0630
0631
0632
0633
0634
0635
0636
0637
0638
0639
0641
0642
0644
0645
0646
0647
0648
0649
0650
0651
0652
0655
0656
0657
0658
0660
0661
0663
0665
0666
0668
0669
0670
0671
0672
0673
0674
0675
0676
0677
0678
0679
0680
0681
0682
0683
0684
0685
0686
0688
0689
0690
0691
0692
0693
0694
0695
0697
0699
0700
0701
0702
0703
0706
0707
0708
0709
0710
0711
0712
0713
0714
0715
0716
0717
0718
0719
0720
0721
0722
0723
0724
0725
0726
0727
0728
0729
0730
0731
0732
0734
0736
0737
0738
0739
0740
0741
0742
0744
0745
0746
0747
0748
0749
0750
0751
0752
0753
0754
0755
0756
0757
0758
0759
0760
0761
0764
0765
0766
0767
0768
0769
0770
0771
0772
0773
0774
0775
0776
0777
0778
0779
0780
0781
0782
0783
0784
0785
0787
0788
0789
0790
0792
0794
0796
0797
0799
0800
0801
0804
0805
0806
0807
0808
0809
0810
0811
0812
0813
0814
0816
0817
0819
0820
0821
0822
0823
0824
0826
0827
0828
0829
0830
0831
0832
0833
0834
0835
0837
0838
0839
0840
0841
0843
0844
0845
0846
0847
0848
0850
0851
0852
0853
0854
0855
0856
0857
0858
0859
0860
0861
0862
0864
0865
0866
0867
0868
0869
0870
0871
0872
0873
0874
0875
0876
0877
0879
0880
0881
0882
0883
0884
0885
0886
0887
0888
0889
0890
0891
0892
0893
0894
0895
0896
0897
0898
0899
0900
0901
0902
0903
0904
0905
0907
0908
0909
0910
0911
0913
0915
0916
0917
0918
0919
0920
0921
0922
0923
0924
0925
0926
0928
0929
0930
0931
0932
0933
0934
0935
0937
0941
0942
0943
0944
0945
0947
0948
0950
0951
0952
0953
0954
0955
0957
0958
0960
0961
0962
0963
0964
0965
0966
0967
0968
0969
0970
0971
0973
0974
0975
0976
0977
0978
0979
0980
0981
0982
0984
0985
0987
0988
0989
0991
0993
0994
0996
0997
0998
0999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
RECORDS (download) 8.9 KB 2023-06-05